Add evaluation results on samsum dataset
#1
by
autoevaluator
HF staff
- opened
README.md
CHANGED
|
@@ -21,6 +21,39 @@ model-index:
|
|
| 21 |
- name: Rouge1
|
| 22 |
type: rouge
|
| 23 |
value: 46.8825
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
---
|
| 25 |
|
| 26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 21 |
- name: Rouge1
|
| 22 |
type: rouge
|
| 23 |
value: 46.8825
|
| 24 |
+
- task:
|
| 25 |
+
type: summarization
|
| 26 |
+
name: Summarization
|
| 27 |
+
dataset:
|
| 28 |
+
name: samsum
|
| 29 |
+
type: samsum
|
| 30 |
+
config: samsum
|
| 31 |
+
split: test
|
| 32 |
+
metrics:
|
| 33 |
+
- name: ROUGE-1
|
| 34 |
+
type: rouge
|
| 35 |
+
value: 45.0692
|
| 36 |
+
verified: true
|
| 37 |
+
- name: ROUGE-2
|
| 38 |
+
type: rouge
|
| 39 |
+
value: 20.9049
|
| 40 |
+
verified: true
|
| 41 |
+
- name: ROUGE-L
|
| 42 |
+
type: rouge
|
| 43 |
+
value: 37.3128
|
| 44 |
+
verified: true
|
| 45 |
+
- name: ROUGE-LSUM
|
| 46 |
+
type: rouge
|
| 47 |
+
value: 40.662
|
| 48 |
+
verified: true
|
| 49 |
+
- name: loss
|
| 50 |
+
type: loss
|
| 51 |
+
value: 5.763935565948486
|
| 52 |
+
verified: true
|
| 53 |
+
- name: gen_len
|
| 54 |
+
type: gen_len
|
| 55 |
+
value: 18.4921
|
| 56 |
+
verified: true
|
| 57 |
---
|
| 58 |
|
| 59 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|